x86/percpu: Define raw_cpu_try_cmpxchg and this_cpu_try_cmpxchg()

Define target-specific raw_cpu_try_cmpxchg_N() and
this_cpu_try_cmpxchg_N() macros. These definitions override
the generic fallback definitions and enable target-specific
optimized implementations.

Signed-off-by: Uros Bizjak <ubizjak@gmail.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Link: https://lore.kernel.org/r/20230830151623.3900-1-ubizjak@gmail.com

Author: ubizjak

arch/x86/include/asm/percpu.h

@@ -210,6 +210,25 @@ do {									\
 	(typeof(_var))(unsigned long) pco_old__;			\
 })
 
+#define percpu_try_cmpxchg_op(size, qual, _var, _ovalp, _nval)		\
+({									\
+	bool success;							\
+	__pcpu_type_##size *pco_oval__ = (__pcpu_type_##size *)(_ovalp); \
+	__pcpu_type_##size pco_old__ = *pco_oval__;			\
+	__pcpu_type_##size pco_new__ = __pcpu_cast_##size(_nval);	\
+	asm qual (__pcpu_op2_##size("cmpxchg", "%[nval]",		\
+				    __percpu_arg([var]))		\
+		  CC_SET(z)						\
+		  : CC_OUT(z) (success),				\
+		    [oval] "+a" (pco_old__),				\
+		    [var] "+m" (_var)					\
+		  : [nval] __pcpu_reg_##size(, pco_new__)		\
+		  : "memory");						\
+	if (unlikely(!success))						\
+		*pco_oval__ = pco_old__;				\
+	likely(success);						\
+})
+
 #if defined(CONFIG_X86_32) && !defined(CONFIG_UML)
 #define percpu_cmpxchg64_op(size, qual, _var, _oval, _nval)		\
 ({									\
@@ -410,13 +429,19 @@ do {									\
 #define raw_cpu_cmpxchg_1(pcp, oval, nval)	percpu_cmpxchg_op(1, , pcp, oval, nval)
 #define raw_cpu_cmpxchg_2(pcp, oval, nval)	percpu_cmpxchg_op(2, , pcp, oval, nval)
 #define raw_cpu_cmpxchg_4(pcp, oval, nval)	percpu_cmpxchg_op(4, , pcp, oval, nval)
+#define raw_cpu_try_cmpxchg_1(pcp, ovalp, nval)	percpu_try_cmpxchg_op(1, , pcp, ovalp, nval)
+#define raw_cpu_try_cmpxchg_2(pcp, ovalp, nval)	percpu_try_cmpxchg_op(2, , pcp, ovalp, nval)
+#define raw_cpu_try_cmpxchg_4(pcp, ovalp, nval)	percpu_try_cmpxchg_op(4, , pcp, ovalp, nval)
 
 #define this_cpu_add_return_1(pcp, val)		percpu_add_return_op(1, volatile, pcp, val)
 #define this_cpu_add_return_2(pcp, val)		percpu_add_return_op(2, volatile, pcp, val)
 #define this_cpu_add_return_4(pcp, val)		percpu_add_return_op(4, volatile, pcp, val)
 #define this_cpu_cmpxchg_1(pcp, oval, nval)	percpu_cmpxchg_op(1, volatile, pcp, oval, nval)
 #define this_cpu_cmpxchg_2(pcp, oval, nval)	percpu_cmpxchg_op(2, volatile, pcp, oval, nval)
 #define this_cpu_cmpxchg_4(pcp, oval, nval)	percpu_cmpxchg_op(4, volatile, pcp, oval, nval)
+#define this_cpu_try_cmpxchg_1(pcp, ovalp, nval)	percpu_try_cmpxchg_op(1, volatile, pcp, ovalp, nval)
+#define this_cpu_try_cmpxchg_2(pcp, ovalp, nval)	percpu_try_cmpxchg_op(2, volatile, pcp, ovalp, nval)
+#define this_cpu_try_cmpxchg_4(pcp, ovalp, nval)	percpu_try_cmpxchg_op(4, volatile, pcp, ovalp, nval)
 
 /*
  * Per cpu atomic 64 bit operations are only available under 64 bit.
@@ -431,6 +456,7 @@ do {									\
 #define raw_cpu_add_return_8(pcp, val)		percpu_add_return_op(8, , pcp, val)
 #define raw_cpu_xchg_8(pcp, nval)		raw_percpu_xchg_op(pcp, nval)
 #define raw_cpu_cmpxchg_8(pcp, oval, nval)	percpu_cmpxchg_op(8, , pcp, oval, nval)
+#define raw_cpu_try_cmpxchg_8(pcp, ovalp, nval)	percpu_try_cmpxchg_op(8, , pcp, ovalp, nval)
 
 #define this_cpu_read_8(pcp)			percpu_from_op(8, volatile, "mov", pcp)
 #define this_cpu_write_8(pcp, val)		percpu_to_op(8, volatile, "mov", (pcp), val)
@@ -440,6 +466,7 @@ do {									\
 #define this_cpu_add_return_8(pcp, val)		percpu_add_return_op(8, volatile, pcp, val)
 #define this_cpu_xchg_8(pcp, nval)		percpu_xchg_op(8, volatile, pcp, nval)
 #define this_cpu_cmpxchg_8(pcp, oval, nval)	percpu_cmpxchg_op(8, volatile, pcp, oval, nval)
+#define this_cpu_try_cmpxchg_8(pcp, ovalp, nval)	percpu_try_cmpxchg_op(8, volatile, pcp, ovalp, nval)
 #endif
 
 static __always_inline bool x86_this_cpu_constant_test_bit(unsigned int nr,